Author:
Tian Kai,Zeng Jiefeng,Song Tianci,Li Zhuliu,Evans Asenso,Li Jiuhao
Abstract
Tomato disease control remains a major challenge in the agriculture sector. Early stage recognition of these diseases is critical to reduce pesticide usage and mitigate economic losses. While many research works have been inspired by the success of deep learning in computer vision to improve the performance of recognition systems for crop diseases, few of these studies optimized the deep learning models to generalize their findings to practical use in the field. In this work, we proposed a model for identifying tomato leaf diseases based on both in-house data and public tomato leaf images databases. Three deep learning network architectures (VGG16, Inception_v3, and Resnet50) were trained and tested. We packaged the trained model into an Android application named TomatoGuard to identify nine kinds of tomato leaf diseases and healthy tomato leaf. The results showed that TomatoGuard could be adopted as a model for identifying tomato diseases with a 99% test accuracy, showing significantly better performance compared with APP Plantix, a widely used APP for general purpose plant disease detection.
Subject
Industrial and Manufacturing Engineering,Mechanical Engineering,Bioengineering
Reference48 articles.
1. Abadi, M. et al. 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org.
2. Bow, S. T. 2002. Pattern recognition and image preprocessing. CRC press.
3. Brahimi, M., Arsenovic, M., Laraba, S., Sladojevic, S., Boukhalfa, K., & Moussaoui, A. 2018. Deep learning for plant diseases: detection and saliency map visualisation. In Human and machine learning (pp. 93-117). Springer, Cham.
4. Brahimi, M., Boukhalfa, K., & Moussaoui, A. 2017. Deep learning for tomato diseases: classification and symptoms visualization. Applied Artificial Intelligence, 31(4):299-315.
5. Chollet, F. et al. 2015. Keras, GitHub. https://github.com/fchollet/keras
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献